INDEX

Explanations

references to dates and publications, particularly in the context of academic or journalistic content

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Text within brackets or parentheses

np_acts-logits-general · gemini-2.0-flash

mathematical bar notation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 zabud

-0.38

انجليز

-0.37

 navideña

-0.37

 mesmas

-0.37

 navideño

-0.37

tagPool

-0.36

 felices

-0.35

 casado

-0.35

 Acerca

-0.34

 descrição

-0.34

POSITIVE LOGITS

 resourceCulture

0.59

/*

0.59

AsUp

0.55

basicConfig

0.50

NameInMap

0.49

 utafitiHapana

0.49

EDEFAULT

0.49

AndEndTag

0.48

CloseOperation

0.47

CompleteListener

0.47

Activations Density 0.235%

references to dates and publications, particularly in the context of academic or journalistic content

Text within brackets or parentheses

mathematical bar notation

No Comments

No Known Activations